Tabular Reinforcement Learning

Tabular reinforcement learning (RL) focuses on solving Markov Decision Processes (MDPs) with discrete state and action spaces, aiming to find optimal policies that maximize cumulative rewards. Current research emphasizes improving sample efficiency through techniques like policy difference estimation and leveraging external knowledge sources, such as language models, to guide exploration in complex environments. These advancements address limitations in scalability and exploration, particularly relevant for applications requiring interpretability and efficient learning in settings with sparse rewards or limited data, such as resource-constrained federated learning scenarios. The resulting improvements in sample complexity and algorithm performance have significant implications for both theoretical understanding of RL and practical deployment in various domains.

Papers

September 25, 2024

Symbolic State Partition for Reinforcement Learning
Mohsen Ghaffari, Mahsa Varshosaz, Einar Broch Johnsen, Andrzej Wąsowski
Reinforcement Learning State Space Tabular Reinforcement Learning Finite State

August 18, 2024

Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph Forecasting
Geethan Sannidhi, Sagar Srinivas Sakhinana, Venkataramana Runkana
Large Language Model Language Model Retrieval Augmented Generation Temporal Knowledge Zero Shot Prompt Tabular Reinforcement Learning

June 11, 2024

Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
Adhyyan Narang, Andrew Wagenmaker, Lillian Ratliff, Kevin Jamieson
Sample Complexity Optimal Policy Contextual Bandit Policy Evaluation Pure Exploration Tabular Reinforcement Learning

May 12, 2024

On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning
Mario Chahoud, Hani Sami, Azzam Mourad, Hadi Otrok, Jamal Bentahar, Mohsen Guizani
Deep Reinforcement Learning Tabular Reinforcement Learning

March 5, 2024

Language Guided Exploration for RL Agents in Text Environments
Hitesh Golchha, Sahil Yerawar, Dhruvesh Patel, Soham Dan, Keerthiram Murugesan
Reinforcement Learning Agent Language Navigation Sequential Decision Making Decision Support Tabular Reinforcement Learning Text Based Environment

October 18, 2023

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
Bhargav Ganguly, Yang Xu, Vaneet Aggarwal
Regret Analysis Quantum Advantage Infinite Horizon Average Reward Markov Decision Process Quantum Speedup Tabular Reinforcement Learning

February 15, 2023

Optimal Sample Complexity of Reinforcement Learning for Mixing Discounted Markov Decision Processes
Shengbo Wang, Jose Blanchet, Peter Glynn
Reinforcement Learning Markov Decision Process Sample Complexity Tabular Reinforcement Learning

November 8, 2022

Reinforcement Learning with Stepwise Fairness Constraints
Zhun Deng, He Sun, Zhiwei Steven Wu, Linjun Zhang, David C. Parkes
Reinforcement Learning Fairness Constraint Tabular Reinforcement Learning Sequential Decision Making Policy

October 31, 2022

Teacher-student curriculum learning for reinforcement learning
Yanick Schraner
Reinforcement Learning Transfer Learning Reinforcement Learning Benchmark Teacher Student Tabular Reinforcement Learning

October 24, 2022

Hardness in Markov Decision Processes: Theory and Practice
Michelangelo Conserva, Paulo Rauber
Reinforcement Learning Markov Decision Process Theoretical Understanding Practice Mode Hardness Result Tabular Reinforcement Learning

June 3, 2022

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville, Marc G. Bellemare
Reinforcement Learning Deep Reinforcement Learning Much Progress Real World Reinforcement Learning Value Based Reinforcement Learning Tabular Reinforcement Learning

May 18, 2022

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
Ian A. Kash, Lev Reyzin, Zishun Yu
Multi Armed Bandit Adversarial Bandit Tabular Reinforcement Learning

February 23, 2022

Learning Relative Return Policies With Upside-Down Reinforcement Learning
Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber, Rupesh Kumar Srivastava
Supervised Learning Based Policy Goal Conditioned Policy Tabular Reinforcement Learning

January 20, 2022

Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs
Jiayu Chen, Jingdi Chen, Tian Lan, Vaneet Aggarwal
Single Agent Factor Graph Tabular Reinforcement Learning Option Discovery

Tabular Reinforcement Learning

Papers

Symbolic State Partition for Reinforcement Learning

Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph Forecasting

Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning

On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning

Language Guided Exploration for RL Agents in Text Environments

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes

Optimal Sample Complexity of Reinforcement Learning for Mixing Discounted Markov Decision Processes

Reinforcement Learning with Stepwise Fairness Constraints

Teacher-student curriculum learning for reinforcement learning

Hardness in Markov Decision Processes: Theory and Practice

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs

Learning Relative Return Policies With Upside-Down Reinforcement Learning

Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs